thinkspread/Qwen3.5-35B-A3B-Q5K-IQ3XXS-GGUF
Text Generation • 35B • Updated • 471
AI & ML interests
On-device LLM inference on Apple Silicon, GGUF quantization, speculative decoding (MTP / DFlash)
Recent Activity
View all activity
models 10
thinkspread/Qwen3.6-35B-A3B-Q5K-IQ3XXS-GGUF
Text Generation • 35B • Updated • 208
thinkspread/Flint-Q4K-IQ3XXS-GGUF-bench
Text Generation • 40B • Updated • 166
thinkspread/Flint-Q6K-IQ3XXS-GGUF
Text Generation • 40B • Updated • 496
thinkspread/gemma-4-E2B-it-Q4_K_S-GGUF
5B • Updated • 101
thinkspread/gemma-4-12b-it-Q4_K_S-GGUF
12B • Updated • 84
thinkspread/gemma-4-12B-it-4bit-MLX-mirror
12B • Updated • 63
thinkspread/gemma-4-E4B-it-Q4_K_S-GGUF-mirror
8B • Updated • 103
thinkspread/gemma-4-12b-it-Q4_K_S-GGUF-mirror
12B • Updated • 65
thinkspread/gemma-4-26B-A4B-it-UD-Q4_K_S-GGUF-mirror
25B • Updated • 106
datasets 0
None public yet